-; RUN: llc -march=x86 -enable-block-placement < %s | FileCheck %s
+; RUN: llc -mtriple=i686-linux < %s | FileCheck %s
declare void @error(i32 %i, i32 %a, i32 %b)
; Check that we sink cold loop blocks after the hot loop body.
; CHECK: test_loop_cold_blocks:
; CHECK: %entry
+; CHECK: %unlikely1
+; CHECK: %unlikely2
; CHECK: %body1
; CHECK: %body2
; CHECK: %body3
-; CHECK: %unlikely1
-; CHECK: %unlikely2
; CHECK: %exit
entry:
ret i32 %sum
}
+define i32 @test_loop_rotate(i32 %i, i32* %a) {
+; Check that we rotate conditional exits from the loop to the bottom of the
+; loop, eliminating unconditional branches to the top.
+; CHECK: test_loop_rotate:
+; CHECK: %entry
+; CHECK: %body1
+; CHECK: %body0
+; CHECK: %exit
+
+entry:
+ br label %body0
+
+body0:
+ %iv = phi i32 [ 0, %entry ], [ %next, %body1 ]
+ %base = phi i32 [ 0, %entry ], [ %sum, %body1 ]
+ %next = add i32 %iv, 1
+ %exitcond = icmp eq i32 %next, %i
+ br i1 %exitcond, label %exit, label %body1
+
+body1:
+ %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+ %0 = load i32* %arrayidx
+ %sum = add nsw i32 %0, %base
+ %bailcond1 = icmp eq i32 %sum, 42
+ br label %body0
+
+exit:
+ ret i32 %base
+}
+
+define i32 @test_no_loop_rotate(i32 %i, i32* %a) {
+; Check that we don't try to rotate a loop which is already laid out with
+; fallthrough opportunities into the top and out of the bottom.
+; CHECK: test_no_loop_rotate:
+; CHECK: %entry
+; CHECK: %body0
+; CHECK: %body1
+; CHECK: %exit
+
+entry:
+ br label %body0
+
+body0:
+ %iv = phi i32 [ 0, %entry ], [ %next, %body1 ]
+ %base = phi i32 [ 0, %entry ], [ %sum, %body1 ]
+ %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+ %0 = load i32* %arrayidx
+ %sum = add nsw i32 %0, %base
+ %bailcond1 = icmp eq i32 %sum, 42
+ br i1 %bailcond1, label %exit, label %body1
+
+body1:
+ %next = add i32 %iv, 1
+ %exitcond = icmp eq i32 %next, %i
+ br i1 %exitcond, label %exit, label %body0
+
+exit:
+ ret i32 %base
+}
+
+define void @test_loop_rotate_reversed_blocks() {
+; This test case (greatly reduced from an Olden bencmark) ensures that the loop
+; rotate implementation doesn't assume that loops are laid out in a particular
+; order. The first loop will get split into two basic blocks, with the loop
+; header coming after the loop latch.
+;
+; CHECK: test_loop_rotate_reversed_blocks
+; CHECK: %entry
+; Look for a jump into the middle of the loop, and no branches mid-way.
+; CHECK: jmp
+; CHECK: %loop1
+; CHECK-NOT: j{{\w*}} .LBB{{.*}}
+; CHECK: %loop1
+; CHECK: je
+
+entry:
+ %cond1 = load volatile i1* undef
+ br i1 %cond1, label %loop2.preheader, label %loop1
+
+loop1:
+ call i32 @f()
+ %cond2 = load volatile i1* undef
+ br i1 %cond2, label %loop2.preheader, label %loop1
+
+loop2.preheader:
+ call i32 @f()
+ %cond3 = load volatile i1* undef
+ br i1 %cond3, label %exit, label %loop2
+
+loop2:
+ call i32 @f()
+ %cond4 = load volatile i1* undef
+ br i1 %cond4, label %exit, label %loop2
+
+exit:
+ ret void
+}
+
define i32 @test_loop_align(i32 %i, i32* %a) {
; Check that we provide basic loop body alignment with the block placement
; pass.
; single-source GCC.
; CHECK: unnatural_cfg2
; CHECK: %entry
-; CHECK: %loop.header
; CHECK: %loop.body1
; CHECK: %loop.body2
; CHECK: %loop.body3
; CHECK: %loop.body4
; CHECK: %loop.inner2.begin
; The loop.inner2.end block is folded
+; CHECK: %loop.header
; CHECK: %bail
entry:
; CHECK: test_unnatural_cfg_backwards_inner_loop
; CHECK: %entry
; CHECK: %body
-; CHECK: %loop1
; CHECK: %loop2b
+; CHECK: %loop1
; CHECK: %loop2a
entry:
%next.phi = phi i32* [ %next.load, %loop2b ], [ %next.var, %loop2a ]
br label %loop1
}
+
+define void @unanalyzable_branch_to_loop_header() {
+; Ensure that we can handle unanalyzable branches into loop headers. We
+; pre-form chains for unanalyzable branches, and will find the tail end of that
+; at the start of the loop. This function uses floating point comparison
+; fallthrough because that happens to always produce unanalyzable branches on
+; x86.
+;
+; CHECK: unanalyzable_branch_to_loop_header
+; CHECK: %entry
+; CHECK: %loop
+; CHECK: %exit
+
+entry:
+ %cmp = fcmp une double 0.000000e+00, undef
+ br i1 %cmp, label %loop, label %exit
+
+loop:
+ %cond = icmp eq i8 undef, 42
+ br i1 %cond, label %exit, label %loop
+
+exit:
+ ret void
+}
+
+define void @unanalyzable_branch_to_best_succ(i1 %cond) {
+; Ensure that we can handle unanalyzable branches where the destination block
+; gets selected as the optimal sucessor to merge.
+;
+; CHECK: unanalyzable_branch_to_best_succ
+; CHECK: %entry
+; CHECK: %foo
+; CHECK: %bar
+; CHECK: %exit
+
+entry:
+ ; Bias this branch toward bar to ensure we form that chain.
+ br i1 %cond, label %bar, label %foo, !prof !1
+
+foo:
+ %cmp = fcmp une double 0.000000e+00, undef
+ br i1 %cmp, label %bar, label %exit
+
+bar:
+ call i32 @f()
+ br label %exit
+
+exit:
+ ret void
+}
+
+define void @unanalyzable_branch_to_free_block(float %x) {
+; Ensure that we can handle unanalyzable branches where the destination block
+; gets selected as the best free block in the CFG.
+;
+; CHECK: unanalyzable_branch_to_free_block
+; CHECK: %entry
+; CHECK: %a
+; CHECK: %b
+; CHECK: %c
+; CHECK: %exit
+
+entry:
+ br i1 undef, label %a, label %b
+
+a:
+ call i32 @f()
+ br label %c
+
+b:
+ %cmp = fcmp une float %x, undef
+ br i1 %cmp, label %c, label %exit
+
+c:
+ call i32 @g()
+ br label %exit
+
+exit:
+ ret void
+}
+
+define void @many_unanalyzable_branches() {
+; Ensure that we don't crash as we're building up many unanalyzable branches,
+; blocks, and loops.
+;
+; CHECK: many_unanalyzable_branches
+; CHECK: %entry
+; CHECK: %exit
+
+entry:
+ br label %0
+
+ %val0 = load volatile float* undef
+ %cmp0 = fcmp une float %val0, undef
+ br i1 %cmp0, label %1, label %0
+ %val1 = load volatile float* undef
+ %cmp1 = fcmp une float %val1, undef
+ br i1 %cmp1, label %2, label %1
+ %val2 = load volatile float* undef
+ %cmp2 = fcmp une float %val2, undef
+ br i1 %cmp2, label %3, label %2
+ %val3 = load volatile float* undef
+ %cmp3 = fcmp une float %val3, undef
+ br i1 %cmp3, label %4, label %3
+ %val4 = load volatile float* undef
+ %cmp4 = fcmp une float %val4, undef
+ br i1 %cmp4, label %5, label %4
+ %val5 = load volatile float* undef
+ %cmp5 = fcmp une float %val5, undef
+ br i1 %cmp5, label %6, label %5
+ %val6 = load volatile float* undef
+ %cmp6 = fcmp une float %val6, undef
+ br i1 %cmp6, label %7, label %6
+ %val7 = load volatile float* undef
+ %cmp7 = fcmp une float %val7, undef
+ br i1 %cmp7, label %8, label %7
+ %val8 = load volatile float* undef
+ %cmp8 = fcmp une float %val8, undef
+ br i1 %cmp8, label %9, label %8
+ %val9 = load volatile float* undef
+ %cmp9 = fcmp une float %val9, undef
+ br i1 %cmp9, label %10, label %9
+ %val10 = load volatile float* undef
+ %cmp10 = fcmp une float %val10, undef
+ br i1 %cmp10, label %11, label %10
+ %val11 = load volatile float* undef
+ %cmp11 = fcmp une float %val11, undef
+ br i1 %cmp11, label %12, label %11
+ %val12 = load volatile float* undef
+ %cmp12 = fcmp une float %val12, undef
+ br i1 %cmp12, label %13, label %12
+ %val13 = load volatile float* undef
+ %cmp13 = fcmp une float %val13, undef
+ br i1 %cmp13, label %14, label %13
+ %val14 = load volatile float* undef
+ %cmp14 = fcmp une float %val14, undef
+ br i1 %cmp14, label %15, label %14
+ %val15 = load volatile float* undef
+ %cmp15 = fcmp une float %val15, undef
+ br i1 %cmp15, label %16, label %15
+ %val16 = load volatile float* undef
+ %cmp16 = fcmp une float %val16, undef
+ br i1 %cmp16, label %17, label %16
+ %val17 = load volatile float* undef
+ %cmp17 = fcmp une float %val17, undef
+ br i1 %cmp17, label %18, label %17
+ %val18 = load volatile float* undef
+ %cmp18 = fcmp une float %val18, undef
+ br i1 %cmp18, label %19, label %18
+ %val19 = load volatile float* undef
+ %cmp19 = fcmp une float %val19, undef
+ br i1 %cmp19, label %20, label %19
+ %val20 = load volatile float* undef
+ %cmp20 = fcmp une float %val20, undef
+ br i1 %cmp20, label %21, label %20
+ %val21 = load volatile float* undef
+ %cmp21 = fcmp une float %val21, undef
+ br i1 %cmp21, label %22, label %21
+ %val22 = load volatile float* undef
+ %cmp22 = fcmp une float %val22, undef
+ br i1 %cmp22, label %23, label %22
+ %val23 = load volatile float* undef
+ %cmp23 = fcmp une float %val23, undef
+ br i1 %cmp23, label %24, label %23
+ %val24 = load volatile float* undef
+ %cmp24 = fcmp une float %val24, undef
+ br i1 %cmp24, label %25, label %24
+ %val25 = load volatile float* undef
+ %cmp25 = fcmp une float %val25, undef
+ br i1 %cmp25, label %26, label %25
+ %val26 = load volatile float* undef
+ %cmp26 = fcmp une float %val26, undef
+ br i1 %cmp26, label %27, label %26
+ %val27 = load volatile float* undef
+ %cmp27 = fcmp une float %val27, undef
+ br i1 %cmp27, label %28, label %27
+ %val28 = load volatile float* undef
+ %cmp28 = fcmp une float %val28, undef
+ br i1 %cmp28, label %29, label %28
+ %val29 = load volatile float* undef
+ %cmp29 = fcmp une float %val29, undef
+ br i1 %cmp29, label %30, label %29
+ %val30 = load volatile float* undef
+ %cmp30 = fcmp une float %val30, undef
+ br i1 %cmp30, label %31, label %30
+ %val31 = load volatile float* undef
+ %cmp31 = fcmp une float %val31, undef
+ br i1 %cmp31, label %32, label %31
+ %val32 = load volatile float* undef
+ %cmp32 = fcmp une float %val32, undef
+ br i1 %cmp32, label %33, label %32
+ %val33 = load volatile float* undef
+ %cmp33 = fcmp une float %val33, undef
+ br i1 %cmp33, label %34, label %33
+ %val34 = load volatile float* undef
+ %cmp34 = fcmp une float %val34, undef
+ br i1 %cmp34, label %35, label %34
+ %val35 = load volatile float* undef
+ %cmp35 = fcmp une float %val35, undef
+ br i1 %cmp35, label %36, label %35
+ %val36 = load volatile float* undef
+ %cmp36 = fcmp une float %val36, undef
+ br i1 %cmp36, label %37, label %36
+ %val37 = load volatile float* undef
+ %cmp37 = fcmp une float %val37, undef
+ br i1 %cmp37, label %38, label %37
+ %val38 = load volatile float* undef
+ %cmp38 = fcmp une float %val38, undef
+ br i1 %cmp38, label %39, label %38
+ %val39 = load volatile float* undef
+ %cmp39 = fcmp une float %val39, undef
+ br i1 %cmp39, label %40, label %39
+ %val40 = load volatile float* undef
+ %cmp40 = fcmp une float %val40, undef
+ br i1 %cmp40, label %41, label %40
+ %val41 = load volatile float* undef
+ %cmp41 = fcmp une float %val41, undef
+ br i1 %cmp41, label %42, label %41
+ %val42 = load volatile float* undef
+ %cmp42 = fcmp une float %val42, undef
+ br i1 %cmp42, label %43, label %42
+ %val43 = load volatile float* undef
+ %cmp43 = fcmp une float %val43, undef
+ br i1 %cmp43, label %44, label %43
+ %val44 = load volatile float* undef
+ %cmp44 = fcmp une float %val44, undef
+ br i1 %cmp44, label %45, label %44
+ %val45 = load volatile float* undef
+ %cmp45 = fcmp une float %val45, undef
+ br i1 %cmp45, label %46, label %45
+ %val46 = load volatile float* undef
+ %cmp46 = fcmp une float %val46, undef
+ br i1 %cmp46, label %47, label %46
+ %val47 = load volatile float* undef
+ %cmp47 = fcmp une float %val47, undef
+ br i1 %cmp47, label %48, label %47
+ %val48 = load volatile float* undef
+ %cmp48 = fcmp une float %val48, undef
+ br i1 %cmp48, label %49, label %48
+ %val49 = load volatile float* undef
+ %cmp49 = fcmp une float %val49, undef
+ br i1 %cmp49, label %50, label %49
+ %val50 = load volatile float* undef
+ %cmp50 = fcmp une float %val50, undef
+ br i1 %cmp50, label %51, label %50
+ %val51 = load volatile float* undef
+ %cmp51 = fcmp une float %val51, undef
+ br i1 %cmp51, label %52, label %51
+ %val52 = load volatile float* undef
+ %cmp52 = fcmp une float %val52, undef
+ br i1 %cmp52, label %53, label %52
+ %val53 = load volatile float* undef
+ %cmp53 = fcmp une float %val53, undef
+ br i1 %cmp53, label %54, label %53
+ %val54 = load volatile float* undef
+ %cmp54 = fcmp une float %val54, undef
+ br i1 %cmp54, label %55, label %54
+ %val55 = load volatile float* undef
+ %cmp55 = fcmp une float %val55, undef
+ br i1 %cmp55, label %56, label %55
+ %val56 = load volatile float* undef
+ %cmp56 = fcmp une float %val56, undef
+ br i1 %cmp56, label %57, label %56
+ %val57 = load volatile float* undef
+ %cmp57 = fcmp une float %val57, undef
+ br i1 %cmp57, label %58, label %57
+ %val58 = load volatile float* undef
+ %cmp58 = fcmp une float %val58, undef
+ br i1 %cmp58, label %59, label %58
+ %val59 = load volatile float* undef
+ %cmp59 = fcmp une float %val59, undef
+ br i1 %cmp59, label %60, label %59
+ %val60 = load volatile float* undef
+ %cmp60 = fcmp une float %val60, undef
+ br i1 %cmp60, label %61, label %60
+ %val61 = load volatile float* undef
+ %cmp61 = fcmp une float %val61, undef
+ br i1 %cmp61, label %62, label %61
+ %val62 = load volatile float* undef
+ %cmp62 = fcmp une float %val62, undef
+ br i1 %cmp62, label %63, label %62
+ %val63 = load volatile float* undef
+ %cmp63 = fcmp une float %val63, undef
+ br i1 %cmp63, label %64, label %63
+ %val64 = load volatile float* undef
+ %cmp64 = fcmp une float %val64, undef
+ br i1 %cmp64, label %65, label %64
+
+ br label %exit
+exit:
+ ret void
+}
+
+define void @benchmark_heapsort(i32 %n, double* nocapture %ra) {
+; This test case comes from the heapsort benchmark, and exemplifies several
+; important aspects to block placement in the presence of loops:
+; 1) Loop rotation needs to *ensure* that the desired exiting edge can be
+; a fallthrough.
+; 2) The exiting edge from the loop which is rotated to be laid out at the
+; bottom of the loop needs to be exiting into the nearest enclosing loop (to
+; which there is an exit). Otherwise, we force that enclosing loop into
+; strange layouts that are siginificantly less efficient, often times maing
+; it discontiguous.
+;
+; CHECK: @benchmark_heapsort
+; CHECK: %entry
+; First rotated loop top.
+; CHECK: .align
+; CHECK: %while.end
+; CHECK: %for.cond
+; CHECK: %if.then
+; CHECK: %if.else
+; CHECK: %if.end10
+; Second rotated loop top
+; CHECK: .align
+; CHECK: %if.then24
+; CHECK: %while.cond.outer
+; Third rotated loop top
+; CHECK: .align
+; CHECK: %while.cond
+; CHECK: %while.body
+; CHECK: %land.lhs.true
+; CHECK: %if.then19
+; CHECK: %if.then19
+; CHECK: %if.then8
+; CHECK: ret
+
+entry:
+ %shr = ashr i32 %n, 1
+ %add = add nsw i32 %shr, 1
+ %arrayidx3 = getelementptr inbounds double* %ra, i64 1
+ br label %for.cond
+
+for.cond:
+ %ir.0 = phi i32 [ %n, %entry ], [ %ir.1, %while.end ]
+ %l.0 = phi i32 [ %add, %entry ], [ %l.1, %while.end ]
+ %cmp = icmp sgt i32 %l.0, 1
+ br i1 %cmp, label %if.then, label %if.else
+
+if.then:
+ %dec = add nsw i32 %l.0, -1
+ %idxprom = sext i32 %dec to i64
+ %arrayidx = getelementptr inbounds double* %ra, i64 %idxprom
+ %0 = load double* %arrayidx, align 8
+ br label %if.end10
+
+if.else:
+ %idxprom1 = sext i32 %ir.0 to i64
+ %arrayidx2 = getelementptr inbounds double* %ra, i64 %idxprom1
+ %1 = load double* %arrayidx2, align 8
+ %2 = load double* %arrayidx3, align 8
+ store double %2, double* %arrayidx2, align 8
+ %dec6 = add nsw i32 %ir.0, -1
+ %cmp7 = icmp eq i32 %dec6, 1
+ br i1 %cmp7, label %if.then8, label %if.end10
+
+if.then8:
+ store double %1, double* %arrayidx3, align 8
+ ret void
+
+if.end10:
+ %ir.1 = phi i32 [ %ir.0, %if.then ], [ %dec6, %if.else ]
+ %l.1 = phi i32 [ %dec, %if.then ], [ %l.0, %if.else ]
+ %rra.0 = phi double [ %0, %if.then ], [ %1, %if.else ]
+ %add31 = add nsw i32 %ir.1, 1
+ br label %while.cond.outer
+
+while.cond.outer:
+ %j.0.ph.in = phi i32 [ %l.1, %if.end10 ], [ %j.1, %if.then24 ]
+ %j.0.ph = shl i32 %j.0.ph.in, 1
+ br label %while.cond
+
+while.cond:
+ %j.0 = phi i32 [ %add31, %if.end20 ], [ %j.0.ph, %while.cond.outer ]
+ %cmp11 = icmp sgt i32 %j.0, %ir.1
+ br i1 %cmp11, label %while.end, label %while.body
+
+while.body:
+ %cmp12 = icmp slt i32 %j.0, %ir.1
+ br i1 %cmp12, label %land.lhs.true, label %if.end20
+
+land.lhs.true:
+ %idxprom13 = sext i32 %j.0 to i64
+ %arrayidx14 = getelementptr inbounds double* %ra, i64 %idxprom13
+ %3 = load double* %arrayidx14, align 8
+ %add15 = add nsw i32 %j.0, 1
+ %idxprom16 = sext i32 %add15 to i64
+ %arrayidx17 = getelementptr inbounds double* %ra, i64 %idxprom16
+ %4 = load double* %arrayidx17, align 8
+ %cmp18 = fcmp olt double %3, %4
+ br i1 %cmp18, label %if.then19, label %if.end20
+
+if.then19:
+ br label %if.end20
+
+if.end20:
+ %j.1 = phi i32 [ %add15, %if.then19 ], [ %j.0, %land.lhs.true ], [ %j.0, %while.body ]
+ %idxprom21 = sext i32 %j.1 to i64
+ %arrayidx22 = getelementptr inbounds double* %ra, i64 %idxprom21
+ %5 = load double* %arrayidx22, align 8
+ %cmp23 = fcmp olt double %rra.0, %5
+ br i1 %cmp23, label %if.then24, label %while.cond
+
+if.then24:
+ %idxprom27 = sext i32 %j.0.ph.in to i64
+ %arrayidx28 = getelementptr inbounds double* %ra, i64 %idxprom27
+ store double %5, double* %arrayidx28, align 8
+ br label %while.cond.outer
+
+while.end:
+ %idxprom33 = sext i32 %j.0.ph.in to i64
+ %arrayidx34 = getelementptr inbounds double* %ra, i64 %idxprom33
+ store double %rra.0, double* %arrayidx34, align 8
+ br label %for.cond
+}
projects / oota-llvm.git / blobdiff